DEV Community

DEV Challenges

This is the official tag for submissions and announcements related to DEV Challenges.

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
Sanity's Knowledge Base stopped 6 of 7 poisoned pages. The 7th fooled Claude Opus 5.

Sanity Challenge Path One Submission
rudratosh profile

Sanity's Knowledge Base stopped 6 of 7 poisoned pages. The 7th fooled Claude Opus 5.

#devchallenge #sanitychallenge #sanity #ai
Comments
7 min read
Curriculum Truth Ledger Path One Agent

Sanity Challenge Path One Submission
rajab_baig_a3929cefc3758b profile

Curriculum Truth Ledger Path One Agent

#devchallenge #sanitychallenge #sanity #ai
Comments
2 min read
Can an AI Agent Know When Not to Act? A Fail-Closed Reliability Benchmark Across Six Models

Kaggle Benchmarking Challenge Submission
tdealer01crypto profile

Can an AI Agent Know When Not to Act? A Fail-Closed Reliability Benchmark Across Six Models

#devchallenge #kagglechallenge #ai #machinelearning
Comments
4 min read
Three perfect scores weren't enough: testing AI outage decisions one fact at a time

Kaggle Benchmarking Challenge Submission
jaredchuvn profile

Three perfect scores weren't enough: testing AI outage decisions one fact at a time

#devchallenge #kagglechallenge #ai #machinelearning
Comments
5 min read
I vibe-coded a Next.js knowledge base that argues with itself

Sanity Challenge Path Two Submission
zkasuran profile

I vibe-coded a Next.js knowledge base that argues with itself

#devchallenge #sanitychallenge #sanity #ai
Comments
4 min read
I built an agent that refuses to answer Next.js from stale docs

Sanity Challenge Path One Submission
zkasuran profile

I built an agent that refuses to answer Next.js from stale docs

#devchallenge #sanitychallenge #sanity #ai
Comments
4 min read
Weaponizing a CVSS 10.0 PoC: Building a Zero-Touch RSC Recon Engine with GitHub Copilot
anuththara2007w profile

Weaponizing a CVSS 10.0 PoC: Building a Zero-Touch RSC Recon Engine with GitHub Copilot

#mlhacks #devchallenge #hackathon
Comments
4 min read
Round Chat: a floating partner chat for debate rounds

Sanity Challenge Path Two Submission
claire_y profile

Round Chat: a floating partner chat for debate rounds

#devchallenge #sanitychallenge #sanity #ai
Comments
11 min read
DevDocs — A Developer Agent Grounded in Real Documentation

Sanity Challenge Path One Submission
adhithyan_b_5d2daadc216e4 profile

DevDocs — A Developer Agent Grounded in Real Documentation

#devchallenge #sanitychallenge #sanity #ai
Comments
6 min read
TechPulse AI — Autonomous Engineering Interview Errata & Verification Agent

Sanity Challenge Path One Submission
rafia_minhaj_2659f96470d2 profile

TechPulse AI — Autonomous Engineering Interview Errata & Verification Agent

#devchallenge #sanitychallenge #sanity #ai
Comments
2 min read
NexusPipeline: Enterprise Data Ingestion Engine with AI Content Querying
jacksonwazea2k profile

NexusPipeline: Enterprise Data Ingestion Engine with AI Content Querying

#devchallenge #sanitychallenge #sanity #ai
Comments
1 min read
Tell Me More (叙能): Sanity Challenge Path One Submission

Sanity Challenge Path One Submission
sword_luan_6dfb4e81cf5f15 profile

Tell Me More (叙能): Sanity Challenge Path One Submission

#sanitychallenge #devchallenge
Comments
12 min read
# CaseGuard: Winning with Uncertainty-Gated Agentic Fraud Investigation on TigerGraph
kanha_9650 profile

# CaseGuard: Winning with Uncertainty-Gated Agentic Fraud Investigation on TigerGraph

#agents #ai #devchallenge #llm
Comments
3 min read
Patchwork: translations that know when they're out of date, published through Sanity

Sanity Challenge Path Two Submission
touko_ursin_77fed0aa92ca0 profile

Patchwork: translations that know when they're out of date, published through Sanity

#sanitychallenge #devchallenge #nextjs #webdev
Comments
4 min read
Before Daybreak — the promise is the branching point

Sanity Challenge Path Two Submission
ben_black_c5eb233a2cb53a2 profile

Before Daybreak — the promise is the branching point

#devchallenge #sanitychallenge #sanity #ai
Comments
4 min read
👋 Sign in for the ability to sort posts by relevant, latest, or top.